Fixed VAE is very low quality

[levi]

Using the built-in upcast fixed vae, fine details like hair come out fuzzy and pixelated. This is particularly present if cog-sdxl is used to generate a full fine tune and then loras are created from the full fine tune from images generated from the model.

Changing to use madebyollin/sdxl-vae-fp16-fix for fp16/bf16 training fixes the issue.

Generation from full fine tune:

Generation from LoRA trained on full fine tune as base model:

[zeke]

Thanks for the heads up, @levi. Would you be able to open a PR to address this?